PCA filtering and probabilistic SOM for network intrusion detection

Abstract

The growth of the Internet and, consequently, the number of interconnected computers, has exposed significant amounts of information to intruders and attackers. Firewalls aim to detect violations according to a predefined rule-set and usually block potentially dangerous incoming traffic. However, with the evolution of attack techniques, it is more difficult to distinguish anomalies from normal traffic. Different detection approaches have been proposed, including the use of machine learning techniques based on neural models such as Self-Organizing Maps (SOMs). In this paper, we present a classification approach that hybridizes statistical techniques and SOM for network anomaly detection. Thus, while Principal Component Analysis (PCA) and Fisher Discriminant Ratio (FDR) have been considered for feature selection and noise removal, Probabilistic Self-Organizing Maps (PSOM) aim to model the feature space and enable distinguishing between normal and anomalous connections.

Towards Effective Network Intrusion Detection: A Hybrid Model Integrating Gini Index and GBDT with PSO

“…The results are listed in Table 6. For a method M, M 41 and M 18 in Table 6 denote M with the 41 and 18 features, respectively. It is evident from Table 6 that the performance of each method with the 18 features is better than that with all 1.…”

“…De la Hoz et al [18] applied statistical techniques and the self-organizing map (SOM) approach to detect network anomalies. Two machine learning techniques, principal component analysis (PCA) and Fisher discriminant ratio (FDR), were considered in their work to remove irrelevant features and noises.…”

“…The basic idea behind a hybrid model is to significantly improve the detection performance by means of combining several machine learning techniques. In general, the styles of existing hybrid models mainly include ensemble classifier [9,11,12], clustering plus classification [13][14][15], and feature selection plus classification [3,4,[16][17][18][19][20][21].…”

Efecto de la longitud de onda en la respuesta dinámica de muros de retención embebidos

“…Para las capas más superficiales de material se consideró una variante del modelo Mohr-Coulomb mediante un comportamiento strain-softening para la degradación de la cohesión en función de la deformación plástica. El ángulo de fricción del material y su cohesión se calibraron en función del esfuerzo de confinamiento utilizando resultados experimentales de ensayos triaxiales homotéticos a deformación constante realizados en materiales granulares gruesos (De la Hoz, 2007).…”

“…Se programó una función FISH (Itasca, 2009) para monitorear la variación del área transversal de la probeta virtual en su parte superior, y de esta forma conocer la variación del esfuerzo vertical actuante en la muestra. El módulo de Young E durante los ensayos virtuales varía en función del esfuerzo de confinamiento efectivo, de acuerdo con la variación propuesta por De la Hoz (2007) replanteada en términos del esfuerzo normal octaédrico: E = 136080(σ oct ) 0.48 , donde E y σ oct están en Pascales. Los ensayos simulados corresponden a los del material P-1 (De la Hoz, 2007), para probetas de 15x30 cm sometidas a esfuerzos de confinamiento de 100, 200 y 400 kPa.…”